About this role
Lead the design and deployment of production AI systems at scale, including architecture, model serving, inference, evaluation, and optimization pipelines. Improve model latency, throughput, quality, and cost, lead technical AI initiatives across teams, mentor AI engineers, and partner with Product and Engineering leadership on AI strategy.
Skills for this role
PythonML engineeringMachine LearningLarge Language Models (LLMs)Model servingInferenceModel evaluationModel optimizationInference optimizationDistributed systemsSystem designProduction LLMsvLLMTGITritonCUDAPyTorchKubernetesGPU infrastructureRAGFine-tuningAI agentsTechnical leadershipMentoringCommunication